maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Add a combine to turn (insert_subvector zero, (insert_subvector zero, X, Idx), Idx) into an insert of X into the larger zero vector. 

llvm-svn: 312460
This commit is contained in:
Craig Topper 2017-09-03 22:25:52 +00:00
parent fcf6bc5503
commit bc13af84f2
3 changed files with 15 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -35656,10 +35656,21 @@ static SDValue combineInsertSubvector(SDNode *N, SelectionDAG &DAG,
unsigned IdxVal = cast<ConstantSDNode>(Idx)->getZExtValue();
MVT SubVecVT = SubVec.getSimpleValueType();
// Inserting zeros into zeros is a nop.
if (ISD::isBuildVectorAllZeros(Vec.getNode()) &&
ISD::isBuildVectorAllZeros(SubVec.getNode()))
return Vec;
if (ISD::isBuildVectorAllZeros(Vec.getNode())) {
// Inserting zeros into zeros is a nop.
if (ISD::isBuildVectorAllZeros(SubVec.getNode()))
return Vec;
// If we're inserting into a zero vector and then into a larger zero vector,
// just insert into the larger zero vector directly.
if (SubVec.getOpcode() == ISD::INSERT_SUBVECTOR &&
ISD::isBuildVectorAllZeros(SubVec.getOperand(0).getNode())) {
unsigned Idx2Val = cast<ConstantSDNode>(Idx)->getZExtValue();
return DAG.getNode(ISD::INSERT_SUBVECTOR, dl, OpVT, Vec,
SubVec.getOperand(1),
DAG.getIntPtrConstant(IdxVal + Idx2Val, dl));
}
}
// If this is an insert of an extract, combine to a shuffle. Don't do this
// if the insert or extract can be represented with a subregister operation.

4
llvm/test/CodeGen/X86/avx512-intrinsics-fast-isel.ll
View File

@ -1134,13 +1134,11 @@ define <8 x double> @test_mm512_zextpd128_pd512(<2 x double> %a0) nounwind {
; X32-LABEL: test_mm512_zextpd128_pd512:
; X32: # BB#0:
; X32-NEXT: vmovaps %xmm0, %xmm0
; X32-NEXT: vmovaps %ymm0, %ymm0
; X32-NEXT: retl
;
; X64-LABEL: test_mm512_zextpd128_pd512:
; X64: # BB#0:
; X64-NEXT: vmovaps %xmm0, %xmm0
; X64-NEXT: vmovaps %ymm0, %ymm0
; X64-NEXT: retq
%res = shufflevector <2 x double> %a0, <2 x double> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 2, i32 3>
ret <8 x double> %res
@ -1196,13 +1194,11 @@ define <8 x i64> @test_mm512_zextsi128_si512(<2 x i64> %a0) nounwind {
; X32-LABEL: test_mm512_zextsi128_si512:
; X32: # BB#0:
; X32-NEXT: vmovaps %xmm0, %xmm0
; X32-NEXT: vmovaps %ymm0, %ymm0
; X32-NEXT: retl
;
; X64-LABEL: test_mm512_zextsi128_si512:
; X64: # BB#0:
; X64-NEXT: vmovaps %xmm0, %xmm0
; X64-NEXT: vmovaps %ymm0, %ymm0
; X64-NEXT: retq
%res = shufflevector <2 x i64> %a0, <2 x i64> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 2, i32 3, i32 2, i32 3>
ret <8 x i64> %res

2
llvm/test/CodeGen/X86/merge-consecutive-loads-512.ll
View File

@ -107,14 +107,12 @@ define <8 x double> @merge_8f64_f64_12zzuuzz(double* %ptr) nounwind uwtable noin
; ALL-LABEL: merge_8f64_f64_12zzuuzz:
; ALL: # BB#0:
; ALL-NEXT: vmovaps 8(%rdi), %xmm0
; ALL-NEXT: vmovaps %ymm0, %ymm0
; ALL-NEXT: retq
;
; X32-AVX512F-LABEL: merge_8f64_f64_12zzuuzz:
; X32-AVX512F: # BB#0:
; X32-AVX512F-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-AVX512F-NEXT: vmovaps 8(%eax), %xmm0
; X32-AVX512F-NEXT: vmovaps %ymm0, %ymm0
; X32-AVX512F-NEXT: retl
%ptr0 = getelementptr inbounds double, double* %ptr, i64 1
%ptr1 = getelementptr inbounds double, double* %ptr, i64 2